Enhance the e2e testing of the ai-proxy plugin based on the LLM mock …

…server

test/e2e/conformance/base/llm-mock.yaml

@@ -0,0 +1,39 @@
+# Copyright (c) 2025 Alibaba Group Holding Ltd.
+#
+# Licensed under the Apache License, Version 2.0 (the "License");
+# you may not use this file except in compliance with the License.
+# You may obtain a copy of the License at
+#
+#      http://www.apache.org/licenses/LICENSE-2.0
+#
+# Unless required by applicable law or agreed to in writing, software
+# distributed under the License is distributed on an "AS IS" BASIS,
+# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+# See the License for the specific language governing permissions and
+# limitations under the License.
+
+apiVersion: v1
+kind: Pod
+metadata:
+  name: llm-mock
+  namespace: higress-conformance-app-backend
+  labels:
+    name: llm-mock
+spec:
+  containers:
+    - name: llm-mock
+      image: registry.cn-hangzhou.aliyuncs.com/hxt/llm-mock:latest
+      ports:
+        - containerPort: 3000
+---
+apiVersion: v1
+kind: Service
+metadata:
+  name: llm-mock-service
+  namespace: higress-conformance-app-backend
+spec:
+  selector:
+    name: llm-mock
+  clusterIP: None
+  ports:
+    - port: 3000

test/e2e/conformance/tests/go-wasm-ai-proxy.go

@@ -27,84 +27,33 @@ func init() {
 
 var WasmPluginsAiProxy = suite.ConformanceTest{
 	ShortName:   "WasmPluginAiProxy",
-	Description: "The Ingress in the higress-conformance-infra namespace test the ai-proxy WASM plugin.",
+	Description: "The Ingress in the higress-conformance-app-backend namespace test the ai-proxy WASM plugin.",
 	Features:    []suite.SupportedFeature{suite.WASMGoConformanceFeature},
 	Manifests:   []string{"tests/go-wasm-ai-proxy.yaml"},
 	Test: func(t *testing.T, suite *suite.ConformanceTestSuite) {
 		testcases := []http.Assertion{
 			{
 				Meta: http.AssertionMeta{
-					TestCaseName:    "case 1: openai",
-					TargetBackend:   "infra-backend-v1",
-					TargetNamespace: "higress-conformance-infra",
+					TestCaseName:    "case 1: minimax",
+					TargetBackend:   "llm-mock-service",
+					TargetNamespace: "higress-conformance-app-backend",
 				},
 				Request: http.AssertionRequest{
 					ActualRequest: http.Request{
-						Host:             "openai.ai.com",
-						Path:             "/v1/chat/completions",
-						Method:"POST",
-						ContentType:      http.ContentTypeApplicationJson,
-						Body: []byte(`{
-							"model": "gpt-3",
-                            "messages": [{"role":"user","content":"hi"}]}`),
-					},
-					ExpectedRequest: &http.ExpectedRequest{
-						Request: http.Request{
-							Host:        "api.openai.com",
-							Path:        "/v1/chat/completions",
-							Method:      "POST",
-							ContentType: http.ContentTypeApplicationJson,
-							Body: []byte(`{
-								"model": "gpt-3",
-                                "messages": [{"role":"user","content":"hi"}],
-                                "max_tokens": 123,
-								"temperature": 0.66}`),
-						},
+						Host:        "openai.ai.com",
+						Path:        "/v1/chat/completions",
+						Method:      "POST",
+						ContentType: http.ContentTypeApplicationJson,
+						Body:        []byte(`{"model":"gpt-3","messages":[{"role":"user","content":"你好，你是谁？"}],"stream":false}`),
 					},
 				},
 				Response: http.AssertionResponse{
 					ExpectedResponse: http.Response{
 						StatusCode: 200,
+						Body:       []byte(`{"id":"chatcmpl-llm-mock","choices":[{"index":0,"message":{"role":"assistant","content":"你好，你是谁？"},"finish_reason":"stop"}],"model":"abab6.5s-chat","object":"chat.completion","usage":{"prompt_tokens":9,"completion_tokens":1,"total_tokens":10}}`),
 					},
 				},
 			},
-			{
-				Meta: http.AssertionMeta{
-					TestCaseName:    "case 2: qwen",
-					TargetBackend:   "infra-backend-v1",
-					TargetNamespace: "higress-conformance-infra",
-				},
-				Request: http.AssertionRequest{
-					ActualRequest: http.Request{
-						Host:             "qwen.ai.com",
-						Path:             "/v1/chat/completions",
-						Method:"POST",
-						ContentType:      http.ContentTypeApplicationJson,
-						Body: []byte(`{
-							"model": "qwen-long",
-							"input": {"messages": [{"role":"user","content":"hi"}]},
-							"parameters": {"max_tokens": 321, "temperature": 0.7}}`),
-					},
-					ExpectedRequest: &http.ExpectedRequest{
-						Request: http.Request{
-							Host:        "dashscope.aliyuncs.com",
-							Path:        "/api/v1/services/aigc/text-generation/generation",
-							Method:      "POST",
-							ContentType: http.ContentTypeApplicationJson,
-							Body: []byte(`{
-							"model": "qwen-long",
-							"input": {"messages": [{"role":"user","content":"hi"}]},
-							"parameters": {"max_tokens": 321, "temperature": 0.66}}`),
-						},
-					},
-				},
-				Response: http.AssertionResponse{
-					ExpectedResponse: http.Response{
-						StatusCode: 500,
-					},
-				},
-			},
-
 		}
 		t.Run("WasmPlugins ai-proxy", func(t *testing.T) {
 			for _, testcase := range testcases {

test/e2e/conformance/tests/go-wasm-ai-proxy.yaml

@@ -14,9 +14,8 @@
 apiVersion: networking.k8s.io/v1
 kind: Ingress
 metadata:
-  annotations:
   name: wasmplugin-ai-proxy-openai
-  namespace: higress-conformance-infra
+  namespace: higress-conformance-app-backend
 spec:
   ingressClassName: higress
   rules:
@@ -27,61 +26,53 @@ spec:
             path: "/"
             backend:
               service:
-                name: infra-backend-v1
+                name: llm-mock-service
                 port:
-                  number: 8080
+                  number: 3000
 ---
 apiVersion: networking.k8s.io/v1
 kind: Ingress
 metadata:
-  annotations:
-  name: wasmplugin-ai-proxy-qwen
-  namespace: higress-conformance-infra
+  name: wasmplugin-ai-proxy-minimax
+  namespace: higress-conformance-app-backend
 spec:
   ingressClassName: higress
   rules:
-    - host: "qwen.ai.com"
+    - host: "api.minimax.chat"
       http:
         paths:
           - pathType: Prefix
             path: "/"
             backend:
               service:
-                name: infra-backend-v1
+                name: llm-mock-service
                 port:
-                  number: 8080
+                  number: 3000
 ---
 apiVersion: extensions.higress.io/v1alpha1
 kind: WasmPlugin
 metadata:
   name: ai-proxy
   namespace: higress-system
 spec:
-  priority: 200
+  defaultConfigDisable: true
+  phase: UNSPECIFIED_PHASE
+  priority: 100
   matchRules:
     - config:
         provider:
           type: "openai"
-          customSettings:
-            - name: "max_tokens"
-              value: 123
-              overwrite: false
-            - name: "temperature"
-              value: 0.66
-              overwrite: true
       ingress:
-        - higress-conformance-infra/wasmplugin-ai-proxy-openai
+        - higress-conformance-app-backend/wasmplugin-ai-proxy-openai
     - config:
         provider:
-          type: "qwen"
-          apiTokens: "fake-token"
-          customSettings:
-            - name: "max_tokens"
-              value: 123
-              overwrite: false
-            - name: "temperature"
-              value: 0.66
-              overwrite: true
+          apiTokens:
+            - fake_token
+          modelMapping:
+            'gpt-3': abab6.5s-chat
+            'gpt-4': abab6.5g-chat
+            '*': abab6.5t-chat
+          type: minimax
       ingress:
-        - higress-conformance-infra/wasmplugin-ai-proxy-qwen
+        - higress-conformance-app-backend/wasmplugin-ai-proxy-minimax
   url: oci://higress-registry.cn-hangzhou.cr.aliyuncs.com/plugins/ai-proxy:1.0.0